Photosynthetic Rate Prediction Model of Greenhouse Crops Based on PLS-ELM

Abstract

Aiming at the problems of low prediction accuracy caused by the large amount of calculation and artificially selected parameters when the traditional extreme learning machine (ELM) algorithm is used to establish the photosynthetic rate prediction model of greenhouse crops, a prediction model of photosynthetic rate based on extreme learning machine combining with partial least squares method (PLS-ELM) is established in this paper. Firstly, the sample data were obtained by measuring the photosynthetic rate under the combination of multiple environmental factors. Secondly, a photosynthetic rate modeling method based on PLS-ELM is proposed, that is, the number of hidden layer neurons and network weights of extreme learning machine algorithm are optimized by partial least squares (PLS), and the Softmax is selected as the activation function to improve the fitting accuracy of the model established by ELM algorithm. Finally, the experimental results show that the photosynthetic rate prediction model established by this method has high accuracy.